liyuming1978

MindMemOS. Python

Agent0. [COLM'26 & ICML'26] Agent0 Series: Self-Evolving Agents from Zero Data

awesome-claude-skills. A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

happy-llm. 📚 从零开始的大语言模型原理与实践教程

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

fast-langdetect. ⚡️ 80x faster Fasttext language detection out of the box | Split text by language

OLMo. Modeling, training, eval, and inference code for OLMo

self-rewarding-lm-pytorch. Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

LLaMA-Rider. Python

Tabular-LLM. 本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。

StreamDiffusion. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

FinGLM. FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

MNBVC. MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

sec-insights. A real world full-stack application using LlamaIndex

versatile_audio_super_resolution. Versatile audio super resolution (any -> 48kHz) with AudioSR.

Langchain-Chatchat. Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

cuad. CUAD (NeurIPS 2021)

Flowise. Build AI Agents, Visually

langflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

kohya_ss. Python

CasRel. [ACL 2020] A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

scratch. Personal scratch code

python-for-android. Turn your Python application into an Android APK

sl4a. SL4A brings scripting languages to Android by allowing you to edit and execute scripts and interactive interpreters directly on the Android device.

vscodium. binary releases of VS Code without MS branding/telemetry/licensing

ScreenRecorderLib. A .NET library for screen recording in Windows, using native Microsoft Media Foundation for realtime encoding to h264 video or PNG images.

trantor-conan. Python

tflite-tools. TFLite model analyzer & memory optimizer

modelbox. A high performance, high expansion, easy to use framework for AI application. 为AI应用的开发者提供一套统一的高性能、易用的编程框架，快速基于AI全栈服务、开发跨端边云的AI行业应用，支持GPU，NPU加速。

TinyNeuralNetwork. TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

FFmpegOpenGL. Android video player, decoded by FFmpeg, render by OpenGL ES 2.0

cpp-httplib. A C++ header-only HTTP/HTTPS server and client library

sion. A single-header, cross-platform C++ library for making asynchronous HTTP(s) Requests.

libco. libco is a coroutine library which is widely used in wechat back-end service. It has been running on tens of thousands of machines since 2013.

Onnx2Text. Converts an ONNX ML model protobuf from/to text, or tensor from/to text/CSV/raw data. (Windows command line tool)

MetalPetal. A GPU accelerated image and video processing framework built on Metal.

directx-sdk-samples-reworked. This repo contains Direct3D 11, XInput, and XAudio2 samples C++ samples from the legacy DirectX SDK updated to build using the Windows 10 SDK

DirectX-Graphics-Samples. This repo contains the DirectX Graphics samples that demonstrate how to build graphics intensive applications on Windows.

amis. 前端低代码框架，通过 JSON 配置就能生成各种页面。

once-for-all. [ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

bitmap_fonts_neon_osd_Draw_yuv. based arm neon , osd draw on yuv data;

FaceRecognition. C++

EasyDarwin. open source、high performance、industrial rtsp streaming server,a lot of optimization on streaming relay,KeyFrame cache,RESTful,and web management,also EasyDarwin support distributed load balancing,a simple streaming media cloud platform architecture.

MVision. 机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

RFBNet. Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018

seed_rl. SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

conan. Conan - The open-source C and C++ package manager

generative_inpainting. DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

OnvifServerSimu. Onvif Server Simulator write by QQ:502706647, device discovery service,rtsp media server,Some key interfaces of onvif

PocketFlow. An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

gstreamer-media-SDK. C

MNN. MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

pai. Resource scheduling and cluster management for AI

nni. An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

DeOldify. A Deep Learning based project for colorizing and restoring old images (and video!)

Decouple-SSAD. Decoupling Localization and Classification in Single Shot Temporal Action Detection

PAFBenchmark. Neuromorphic Vision Datasets for Pedestrian Detection, Action Recognition, and Fall Detection

threadpool. based on C++11 , a mini threadpool , accept variable number of parameters 基于C++11的线程池,简洁且可以带任意多的参数

WebKit-http. Deprecated unofficial http mirror of the WebKit SVN repository

android-gpuimage. Android filters based on OpenGL (idea from GPUImage for iOS)

packages-apps-Camera2. packages/apps/Camera2

camera. Kotlin

HandTracker. 3D Hand Tracking using input from a depth sensor.

python-lite-camera. A lightweight, cross-platform library for capturing RGB frames from cameras

AISkillsForWindows. Contains samples for implementing Windows Skills by extending the preview base API and using exsting skill packages

onnx-tensorrt. ONNX-TensorRT: TensorRT backend for ONNX

HyperPose. Library for Fast and Flexible Human Pose Estimation

dlADMM. dlADMM: Deep Learning Optimization via Alternating Direction Method of Multipliers

TensorRT. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

mediapipe. Cross-platform, customizable ML solutions for live and streaming media.

Instaboost. Code for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting"

RefineDet_TensorFlow. A TensorFlow implementation of the RefineDet object detector model.

modified_refinedet. Modified RefineDet

PyramidBox. This repo implements PyramidBox with pytorch

MedicalNet. Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

wux-weapp. :dog: 一套组件化、可复用、易扩展的微信小程序 UI 组件库

coloruicss. 鲜亮的高饱和色彩，专注视觉的小程序组件库

tensorflow-windows-wheel. Tensorflow prebuilt binary for Windows

SogouMRCToolkit. This toolkit was designed for the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.

deep-learning-models. Keras code and weights files for popular deep learning models.

Deep-Lesion. A deep learning framework for detecting lesions in CT scans from Deep Lesion dataset

keras. Deep Learning for humans

AnatomyNet-for-anatomical-segmentation. AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation

CADLab. Imaging Biomarkers and Computer-Aided Diagnosis Laboratory

numpy-ml. Machine learning, in numpy

medical-data.

Deep-Flow-Guided-Video-Inpainting. pytorch implementation for "Deep Flow-Guided Video Inpainting"(CVPR'19)

sparse_attention. Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

OctaveConv_pytorch. Pytorch implementation of newly added convolution

OctaveConv. A MXNet Implementation for Drop an Octave

hand_tracking_samples. :wave: :ok_hand: research codebase for depth-based hand pose estimation using dynamics based tracking and CNNs

cppjieba. "结巴"中文分词的C++版本

shufflenet-v2-tensorflow. A lightweight convolutional neural network

Shufflenet-v2-Pytorch. Perfect implement. Model shared. x0.5 (Top1:60.646) and 1.0x (Top1:69.402).

ShuffleNet_V2_pytorch_caffe. ShuffleNet-V2 for both PyTorch and Caffe.

CPS-OCR-Engine. An awesome OCR engine developed by SYSU DeepDriving Lab

QASystemOnMedicalKG. A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。

catseye. Neural network library written in C and Javascript

differ. Developing preservation processes for a trusted digital repository requires the utilization of new methods and technologies, which have helped to accelerate the whole process of control. The current approach at the Digital Preservation Standards Department at The National Library of the Czech Republic is to develop a quality control application for still image file formats capable of performing identification, characterization, validation and visual/mathematical comparison integrated into an operational digital preservation framework. The online application DIFFER is utilizing existing tools (JHOVE, FITS, ExifTool, KDU_expand, DJVUDUMP, Jpylyzer, etc.), which are mainly used separately across a whole spectrum of existing projects. This open source application comes with a well-structured and uniform GUI, which helps the user to understand the relationships between various file format properties, detect visual and non-visual errors and simplifies decision-making. An additional feature called compliance-check is designed to help us check the required specifications of the JPEG2000 file format.

sdm. Supervised Descent Method Apply to Face Alignment, and Head Pose Estimation with Linear Regression. It is cross-platfrom, easily compile in windows, ubuntu, even in Android & iOS.

ShuffeNet-Tracker. human tracking on an ARM chip(RK3399)

mpp_rtsp_player. 开发板为RK3399-firefly，使用mpp进行做硬解码，显示使用X11+OpenGL ES 2.0

onvif-java-lib. ONVIF (Open Network Video Interface Forum) is a community to standardize communication between IP-based security products (like cameras). I developed a Java library for the ONVIF spezification. It helps you with the basics (you don't need to learn SOAP e.g.) but you may need to learn a few basics about the ONVIF spezification. As far as I know, this is the first public Java project for the ONVIF spezification.

python-onvif. ONVIF Client Implementation in Python

IPCameraDiscoveryWithQt. IP Camera ONVIF device discovery with wsdl/soap in Qt/C++

SEAL. Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

taro. 开放式跨端跨框架解决方案，支持使用 React/Vue 等框架来开发微信/京东/百度/支付宝/字节跳动/ QQ 小程序/H5/React Native 等应用。 https://taro.zone/

react-native-openalpr. An open-source React Native automatic license plate recognition package for OpenALPR

HyperLandmark. Deep Learning Based Free Mobile Real-Time Face Landmark Detector. Contact:jack-yu-business@foxmail.com

drishti. Real time eye tracking for embedded and mobile devices.

caffe-int8-convert-tools. Generate a quantization parameter file for ncnn framework int8 inference

Realtime_Multi-Person_Pose_Estimation. Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

caffe-int8-convert-tools. This convert tools is base on TensorRT 2.0 Int8 calibration tools,which use the KL algorithm to find the suitable threshold to quantize the activions from Float32 to Int8(-128 - 127).

tvm. Open Machine Learning Compiler Framework

Tengine. Tengine is a lite, high performance, modular inference engine for embedded device

ComputeLibrary. The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

san. A fast, portable, flexible JavaScript component framework

cxxurl. Not only a c++ wrapper for curl

backgroundblur. blur;Bokeh;opencv;grabCut,这个一个运用抠图技术实现的背景虚化功能，主要模仿高端相机的背景虚化或者背景模糊效果

battery-historian. Battery Historian is a tool to analyze battery consumers using Android "bugreport" files.

TensorRT_test. TensorRT sample integrated in Windows Platform with Visual Studio 2017. The release is TensorRT5.0.

Awesome-TensorFlow-Chinese. Awesome-TensorFlow-Chinese，TensorFlow 中文资源精选，官方网站，安装教程，入门教程，视频教程，实战项目，学习路径。QQ群：167122861，公众号：磐创AI，微信群二维码：http://www.tensorflownews.com/

tensorflow-tutorial-samples. TensorFlow2教程 TensorFlow 2.0 Tutorial 入门教程实战案例

tensorflow-onnx. Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

RAISR. Implement of "RAISR: Rapid and Accurate Image Super Resolution"

face_swap. End-to-end, automatic face swapping pipeline

android-faceeffect. a demo of face effect like faceu

MARFaceBeauty. 一款类似于FaceU的美颜相机，支持大部分基础功能：美颜，对焦，前后摄像头转换，过场动画...

beauty. Android实现的瘦脸、放大眼睛的算法

python-compare-images. This repository is mainly about comparing two images. The technique used is SSIM. i.e. Structural Similarity Index Measure We use some of the inbuilt functions available in python's skimage library to measure the SSIM value. Along with SSIM we also measure the MSE ( Mean Square Error ) To know more about the SSIM technique Refer Here: https://en.wikipedia.org/wiki/Structural_similarity

data-science-bowl-2018. End-to-end one-class instance segmentation based on U-Net architecture for Data Science Bowl 2018 in Kaggle

video-quality. Video quality metrics, reference implementation in python: VIF, SSIM, PSNR, ...

deep_learning_object_detection. A paper list of object detection using deep learning.

FaceSwap. Real-time FaceSwap application built with OpenCV and dlib

FaceSwap. 3D face swapping implemented in Python

FaceSwap. Swap face between two photos.

faceswap. Deepfakes Software For All

GPU-tracking. Final project for 15-618 : implement a GPU version of the KCF algorithm

tensorflow2caffemodel. tensorflow 2 caffe model

pytorch-dense-correspondence. Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"

demo_mobilenetv2_deeplabv3. semantic segmentation demo bases on https://github.com/lizhengwei1992/models/tree/master/research/deeplab

mobile-semantic-segmentation. Real-Time Semantic Segmentation in Mobile device

Flow-Guided-Feature-Aggregation. Flow-Guided Feature Aggregation for Video Object Detection

pexels_downloader. Download images from pexels.com

Wave-U-Net. Implementation of the Wave-U-Net for audio source separation

Tensorflow-Tutorial. Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学

models. Models and examples built with TensorFlow

FFmpegPlayer. Simple FFmpeg video player

super-resolution. collection of super-resolution models & algorithms

Windows-classic-samples. This repo contains samples that demonstrate the API used in Windows classic desktop applications.

fanplayer. A portable video player based on ffmpeg for windows and android platform.

SqueezeNext.

SqueezeNet. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

TensorFlow-Examples. TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

mace. MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

hdrcnn. HDR image reconstruction from a single exposure using deep CNNs

deep3d. Automatic 2D-to-3D Video Conversion with CNNs

compute-runtime. Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver

mobilefacenet-caffe. a caffe implementation of mobilefacenet,with the record of trainnig log

pytorch2caffe. Convert PyTorch model to Caffemodel

DRRN_CVPR17. Code for our CVPR'17 paper "Image Super-Resolution via Deep Recursive Residual Network"

caffe_srgan. A Caffe Implementation of SRGAN

magnum. Lightweight and modular C++11 graphics middleware for games and data visualization

face-landmark-android. Android AR Camera

MagicCamera. Real-time Filter Camera&VideoRecorder And ImageEditor With Face Beauty For Android---包含美颜等40余种实时滤镜相机，可拍照、录像、图片修改

avatar-facial-landmark-detection. A method about optimizing the facial landmark detection based on Kalman Filter, Optical Flow and Dlib

netron. Visualizer for neural network, deep learning and machine learning models

FULivePC. Faceunity 面部跟踪和虚拟道具 SDK 在 PC 平台中的集成 Demo

Virtual-Device-Camera. 虚拟驱动摄像头 虚拟驱动摄像头 Virtual driving camera

head-pose-estimation. Realtime human head pose estimation with ONNXRuntime and OpenCV.

head-pose-estimation. Real-time head pose estimation built with OpenCV and dlib

gpu-switch. gpu-switch is an application that allows to switch between the graphic cards of dual-GPU Macbook Pro models

clinfo. Print all known information about all available OpenCL platforms and devices in the system

Facial-Landmark. Use transfer learnig(VGGFace) to detect facial landmark. Alse use MobileNet to compresse(mean absolute error is 0.964)

mpc-hc. MPC-HC's main repository. For support use our Trac: https://trac.mpc-hc.org/

SFD. S³FD: Single Shot Scale-invariant Face Detector, ICCV, 2017

SeetaFaceEngine. C++

cnn-facial-landmark. Training code for facial landmark detection based on deep convolutional neural network.

TrafficLightsDetection. using SSD and caffe detect traffic lights on LISA dataset

Intel_FFmpeg_plugins. mirror of git://source.ffmpeg.org/ffmpeg.git

MediaSDK. The Intel® Media SDK

face-landmark-localization. cnn network predict face landmarks (68 points) and head pose (3d pose, yaw,roll,pitch).

xbyak. A JIT assembler for x86/x64 architectures supporting FPU, MMX, SSE (1-4), AVX (1-2, 512), APX, and AVX10.2

Employee-Management-System. Employee Management System is a desktop based application developed on C# programming language.

ARM_NEON_2_x86_SSE. The platform independent header allowing to compile any C/C++ code containing ARM NEON intrinsic functions for x86 target systems using SIMD up to AVX2 intrinsic functions

mobile-id. Deep Face Model Compression

handong1587.github.io. CSS

caffe-windows. Configure Caffe in one hour for Windows users.

darknet-mobilenet. mobilenet model in darknet framework , MobilenetYOLO, compress mobilenet

ros_intel_movidius_ncs. C++

annoy. Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

deep-learning-model-convertor. The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

onnx. Open standard for machine learning interoperability

libfacedetection. An open source library for face detection in images. The face detection speed can reach 1000FPS.

JDA. C++ implementation of Joint Cascade Face Detection and Alignment.

DeepAlignmentNetwork. A deep neural network for face alignment

head-pose-estimation-and-face-landmark. head pose estimation

caffe-model. Caffe models (including classification, detection and segmentation) and deploy files for famouse networks

Simd. C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON, SVE for ARM, HVX for Hexagon

MMdnn. MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.